dust-tt / llama-ssp
Experiments on speculative sampling with Llama models
☆125Updated last year
Alternatives and similar repositories for llama-ssp:
Users that are interested in llama-ssp are comparing it to the libraries listed below
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆206Updated 10 months ago
- Multipack distributed sampler for fast padding-free training of LLMs☆186Updated 7 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆92Updated last year
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆217Updated 11 months ago
- ☆194Updated 3 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆117Updated last year
- Code repository for the c-BTM paper☆106Updated last year
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆75Updated last year
- scalable and robust tree-based speculative decoding algorithm☆339Updated last month
- Manage scalable open LLM inference endpoints in Slurm clusters☆253Updated 8 months ago
- DSIR large-scale data selection framework for language model training☆243Updated 11 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆154Updated 9 months ago
- Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper☆128Updated 8 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆122Updated 7 months ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆271Updated last year
- A pipeline for LLM knowledge distillation☆98Updated last month
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆150Updated last year
- Pre-training code for Amber 7B LLM☆165Updated 10 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆198Updated 3 months ago
- ☆125Updated last year
- KV cache compression for high-throughput LLM inference☆117Updated last month
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆148Updated 2 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated 9 months ago
- ☆116Updated last month
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆140Updated 6 months ago
- Explorations into some recent techniques surrounding speculative decoding☆248Updated 3 months ago
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆453Updated last year
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆313Updated 5 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.☆224Updated last week